Borrowing it
Nothing to install: this file belongs to AHepi/DeepReason. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AHepi/DeepReason/main/CLAUDE.mdgit clone --depth 1 https://github.com/AHepi/DeepReasonWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/ahepi/deepreason/claude-md)<a href="https://agentmods.dev/instructions/ahepi/deepreason/claude-md"><img src="https://agentmods.dev/badge/instructions/ahepi/deepreason/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/ahepi/deepreason/claude-md"><img src="https://agentmods.dev/badge/instructions/ahepi/deepreason/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.12033 | $0.12033 |
| Opus 5.5 | $0.04813 | $0.04813 |
| Sonnet 5.5 | $0.02407 | $0.02407 |
| Haiku 4.5 | $0.01203 | $0.01203 |
Grade A, and why
DeepReason CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 834 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — operating DeepReason
DeepReason is a Popperian reasoning harness: it drives a provider model
(qwen3.5:397b on Ollama Cloud for every committed launch since
2026-08-25; glm-5.2 wrote most of the earlier corpus and remains a
registered choice) through conjecture–criticism cycles
over an append-only, replay-verifiable record. Everything meaningful is
TYPED — stops, denials, refusals, capability lifecycles — and the record
is the only admissible evidence about what a run did. Model prose is
never evidence; log.jsonl, objects/, progress.jsonl,
run-status.json, REPLAY_VALIDATION.json, and verify_root are.
MANDATORY for every model working in Claude Code on this repository
Never verify a review without the operator's explicit permission.
Operator's words, verbatim (2026-09-05): "Don't not ever verify a review
without my explicit permission. Make it for every model working in Claude
Code and make it mandatory." Operational reading, binding on the monitor,
every executor window, every subagent and every audit or review window:
a review-kind task (an audit, a code review, a verdict on a delivered
branch, a monitor merge review) READS and REPORTS; it does not run the
full gate, docs_verify, the wheel smokes, a soak, a live call, or any
other verification instrument to "confirm" what it is reviewing, unless
the operator has said so for that task in so many words. Reproducing a
single cited check by its own command, where the review brief names it, is
reading; anything wider is verification and needs permission. This applies
to the monitor's post-merge test rings too: none without permission. The
incident: the 2026-09-05 spec-drift audit ran the whole 5,167-test gate for
69 minutes by a mistyped ring command in a read-only window. "I did not
mean to" is not permission. Recorded in the operator design laws below as
well; this block is here so it is the first rule read.
Which workflow to use
Both families now begin with a MAP PREFLIGHT: resolve the work to
DR-SUB-/DR-CON-/DR-SEAM- ids from docs/map/INDEX.md, read the seam
before the subsystems, and read INV-frozen-surfaces.md before designing.
Record the ids in the tranche's first artifact so every later phase starts
from the same map.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +10 lines · +171 tokens per session 992ed85e49a0
- 1mo ago Changed · +44 lines · +671 tokens per session 9d43e4893cb2
- 1mo ago Changed · +19 lines · +281 tokens per session a447dc87c302
- 1mo ago Changed · +125 lines · +2,008 tokens per session 7313bbb8ef7f
- 2mo ago First seen · 636 lines · 8,902 tokens per session scan A 73c4ebf494f3
DeepReason CLAUDE.md is an instructions file published in the GitHub repository AHepi/DeepReason (141 stars, last pushed 1mo ago), licensed MIT. It adds 12,033 tokens to every session, about $0.0481 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.